5 March 2008 A method for image matching based on epipolar geometry
Author Affiliations +
Proceedings Volume 6623, International Symposium on Photoelectronic Detection and Imaging 2007: Image Processing; 66231I (2008) https://doi.org/10.1117/12.791515
Event: International Symposium on Photoelectronic Detection and Imaging: Technology and Applications 2007, 2007, Beijing, China
Abstract
2D image matching is a precondition for 3D object reconstruction, and plays an important role in machine vision. The key of image matching is that establishes the correspondence between images. The fundamental matrix encapsulates all the information between two images. Hence, precise estimation of the fundamental matrix is very important. Due to noise disturbing and correspondence outliers, it is hard to estimate the fundamental matrix. Aiming at this problem, the paper puts forward a new eight-point algorithm which integrates the normalization and LMS algorithm ( least median square) together, solving error estimation result, because of wrong matching points. Through the method above, the result of experiment indicates that the method has higher matching precision. It can be used for multi objects image matching.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hongyu Guo, Hongyu Guo, Yan Han, Yan Han, Jian Wang, Jian Wang, } "A method for image matching based on epipolar geometry", Proc. SPIE 6623, International Symposium on Photoelectronic Detection and Imaging 2007: Image Processing, 66231I (5 March 2008); doi: 10.1117/12.791515; https://doi.org/10.1117/12.791515
PROCEEDINGS
7 PAGES


SHARE
Back to Top